The rise of materials informatics and artificial intelligence (AI)-based computational discovery of materials provides new sources of research directions for materials science. New research demonstrates the enormous potential for experimentalists in photonics for photovoltaic materials to increase the rate of screening and optimization of materials properties and related devices. AI for materials is not only interested in the accuracy of predictive models but also in the effect of data size. Recent investigations have shown significant progress in AI for small data by combining a design of experiments (DoE) approach with machine learning (ML) analysis, which enables experimentalists to use scarce resources more effectively for materials optimization with a higher probability of arriving at a true optimum.
In this work, we propose an alternative approach to DoE associated with ML by using the concept of active learning (AL). AL is well appropriate in industry and physical sciences, where there is a strong need to minimize the number of costly experiments necessary to train predictive models. We focus on optimizing processes of organic photovoltaic (OPV) cells. The manufacturing of OPV devices requires on the case of having a very small labeling budget, about a few dozen data points, and developing a simple and fast method for practical AL with a model selection. Then, we discuss the challenges in anticipating the data-driven process design, such as the complexity of the experimental approach of OPV cells, the diversity of experiment parameters, and the necessary programming ability.
KEYWORDS: Control systems, Actuators, Microactuators, Sensors, Image compression, Microsystems, Field programmable gate arrays, CCD cameras, Mobile robots, Microelectromechanical systems
In the present work, the authors were focused on control modes used in distributed microsystems. Especially, they studied distributed manipulation like motion active surface that have been an important topic in micro and nanofabrication field. After comparing advantages and drawbacks between centralized, decentralized and distributed control systems, they decided to apply the control mode to an airflow active surface based on pneumatic microactuator array, and fabricated by MEMS technology. The size of the device is about 35x35 mm2 for 560 MEMS-based actuators and holes respectively at the front- and the back-side of the silicon substrate. In a first approach, and to overcome fabrication problems of the micro-smart system, combining electronic and electro mechanic elements, a co-design software/hardware solution was implemented. By this way, and using a digital image captured from a CCD camera, autonomy of the distributed microsystems could be developed. Afterward, a feedback control strategy was elaborated by applying principles of autonomous mobile robots that lend it to. A first prototype, validating all control mode principles was successfully implemented directly in software. Experiment results demonstrated advantages and good performances of the method.
In this paper, a design approach was proposed to define suitable structures of distributed controlled MEMS used in a pneumatic two-dimensional microconveyance system. After an introduction to distributed systems, a brief survey of their applications in the field of micromanipulation and prospect in industrial microfabrication was presented. Afterward, the authors introduced the notion of intelligent motion surface used in the field of pneumatic microconveyance. They analyzed suitable distributed structures based on elementary microconveyance, which are supposed to provide an appropriate air-flow force and overcome microfluidic problems. The first microconveyer prototype was fabricated by using bulk micromachining technique. It was developed to estimate MEMS density required to produce an elementary force to convey a micro-object. Then, a specific distributed structure was proposed to develop the pneumatic two-dimensional microconveyer device. The device size is 35 x 35 mm2 for 560 MEMS-microvalves, controlled by distributed arrays and processed by a centralized intelligence via a microprocessor. From experimental conveyance results, we can conclude to the feasibility of the pneumatic microconveyance by distributed air-flow microactuators.
In this paper, the authors proposed to study a model and a control strategy of a two-dimensional conveyance system based on the principles of the Autonomous Decentralized Microsystems (ADM). The microconveyance system is based on distributed cooperative MEMS actuators which can produce a force field onto the surface of the device to grip and move a micro-object. The modeling approach proposed here is based on a simple model of a microconveyance system which is represented by a 5 x 5 matrix of cells. Each cell is consisted of a microactuator, a microsensor, and a microprocessor to provide actuation, autonomy and decentralized intelligence to the cell. Thus, each cell is able to identify a micro-object crossing on it and to decide by oneself the appropriate control strategy to convey the micro-object to its destination target. The control strategy could be established through five simple decision rules that the cell itself has to respect at each calculate cycle time. Simulation and FPGA implementation results are given in the end of the paper in order to validate model and control approach of the microconveyance system.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.